Detection of COVID-19 from CT and Chest X-ray Images Using Deep Learning Models

Integrating ensemble and machine learning models for early prediction of pneumonia mortality using laboratory tests

Background

The recent use of artificial intelligence (AI) in medical research is noteworthy. However, most research has focused on medical imaging. Although the importance of laboratory tests in the clinical field is acknowledged by clinicians, they are undervalued in medical AI research. Our study aims to develop an early prediction AI model for pneumonia mortality, primarily using laboratory test results.

Materials and methods

We developed a mortality prediction model using initial laboratory results and basic clinical information of patients with pneumonia. Several machine learning (ML) models and a deep learning method-multilayer perceptron (MLP)-were selected for model development. The area under the receiver operating characteristic curve (AUROC) and F1-score were optimized to improve model performance. In addition, an ensemble model was developed by blending several models to improve the prediction performance. We used 80,940 data instances for model development.

Results

Among the ML models, XGBoost exhibited the best performance (AUROC = 0.8989, accuracy = 0.88, F1-score = 0.80). MLP achieved an AUROC of 0.8498, accuracy of 0.86, and F1-score of 0.75. The performance of the ensemble model was the best among the developed models, with an AUROC of 0.9006, accuracy of 0.90, and F1-score of 0.81. Several laboratory tests were conducted to identify risk factors that affect pneumonia mortality using the "Feature importance" technique and SHapley Additive exPlanations. We identified several laboratory results, including systolic blood pressure, serum glucose level, age, aspartate aminotransferase-to-alanine aminotransferase ratio, and monocyte-to-lymphocyte ratio, as significant predictors of mortality in patients with pneumonia.

Conclusions

Our study demonstrates that the ensemble model, incorporating XGBoost, CatBoost, and LGBM techniques, outperforms individual ML and deep learning models in predicting pneumonia mortality. Our findings emphasize the importance of integrating AI techniques to leverage laboratory test data effectively, offering a promising direction for advancing AI applications in medical research and clinical decision-making.

[Dielectric properties of tidal volume changes in rabbit lung tissue in the 100 MHz~1 GHz band]

This paper investigates the variation of lung tissue dielectric properties with tidal volume under in vivo conditions to provide reliable and valid a priori information for techniques such as microwave imaging. In this study, the dielectric properties of the lung tissue of 30 rabbits were measured in vivo using the open-end coaxial probe method in the frequency band of 100 MHz to 1 GHz, and 6 different sets of tidal volumes (30, 40, 50, 60, 70, 80 mL) were set up to study the trends of the dielectric properties, and the data at 2 specific frequency points (433 and 915 MHz) were analyzed statistically. It was found that the dielectric coefficient and conductivity of lung tissue tended to decrease with increasing tidal volume in the frequency range of 100 MHz to 1 GHz, and the differences in the dielectric properties of lung tissue for the 6 groups of tidal volumes at 2 specific frequency points were statistically significant. This paper showed that the dielectric properties of lung tissue tend to vary non-linearly with increasing tidal volume. Based on this, more accurate biological tissue parameters can be provided for bioelectromagnetic imaging techniques such as microwave imaging, which could provide a scientific basis and experimental data support for the improvement of diagnostic methods and equipment for lung diseases.

Lung Ultrasonography in the Evaluation of Late Sequelae of COVID-19 Pneumonia-A Comparison with Chest Computed Tomography: A Prospective Study

The onset of the COVID-19 pandemic allowed physicians to gain experience in lung ultrasound (LUS) during the acute phase of the disease. However, limited data are available on LUS findings during the recovery phase. The aim of this study was to evaluate the utility of LUS to assess lung involvement in patients with post-COVID-19 syndrome. This study prospectively enrolled 72 patients who underwent paired LUS and chest CT scans (112 pairs including follow-up). The most frequent CT findings were ground glass opacities (83.3%), subpleural lines (72.2%), traction bronchiectasis (37.5%), and consolidations (31.9%). LUS revealed irregular pleural lines as a common abnormality initially (56.9%), along with subpleural consolidation >2.5 mm ≤10 mm (26.5%) and B-lines (26.5%). A strong correlation was found between LUS score, calculated by artificial intelligence percentage involvement in ground glass opacities described in CT (r = 0.702, p < 0.05). LUS score was significantly higher in the group with fibrotic changes compared to the non-fibrotic group with a mean value of 19.4 ± 5.7 to 11 ± 6.6, respectively (p < 0.0001). LUS might be considered valuable for examining patients with persistent symptoms after recovering from COVID-19 pneumonia. Abnormalities identified through LUS align with CT scan findings; thus, LUS might potentially reduce the need for frequent chest CT examinations.

A Promising Start and Not a Panacea: ChatGPT's Early Impact and Potential in Medical Science and Biomedical Engineering Research

The advent of artificial intelligence (AI) has catalyzed a revolutionary transformation across various industries, including healthcare. Medical applications of ChatGPT, a powerful language model based on the generative pre-trained transformer (GPT) architecture, encompass the creation of conversational agents capable of accessing and generating medical information from multiple sources and formats. This study investigates the research trends of large language models such as ChatGPT, GPT 4, and Google Bard, comparing their publication trends with early COVID-19 research. The findings underscore the current prominence of AI research and its potential implications in biomedical engineering. A search of the Scopus database on July 23, 2023, yielded 1,096 articles related to ChatGPT, with approximately 26% being medical science-related. Keywords related to artificial intelligence, natural language processing (NLP), LLM, and generative AI dominate ChatGPT research, while a focused representation of medical science research emerges, with emphasis on biomedical research and engineering. This analysis serves as a call to action for researchers, healthcare professionals, and policymakers to recognize and harness AI's potential in healthcare, particularly in the realm of biomedical research.

Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE-artificial intelligence project

OBJECTIVES

Artificial intelligence (AI) may be practical for image classification of small bowel capsule endoscopy (CE). However, creating a functional AI model is challenging. We attempted to create a dataset and an object detection CE AI model to explore modeling problems to assist in reading small bowel CE.

METHODS

We extracted 18,481 images from 523 small bowel CE procedures performed at Kyushu University Hospital from September 2014 to June 2021. We annotated 12,320 images with 23,033 disease lesions, combined them with 6161 normal images as the dataset, and examined the characteristics. Based on the dataset, we created an object detection AI model using YOLO v5 and we tested validation.

RESULTS

We annotated the dataset with 12 types of annotations, and multiple annotation types were observed in the same image. We test validated our AI model with 1396 images, and sensitivity for all 12 types of annotations was about 91%, with 1375 true positives, 659 false positives, and 120 false negatives detected. The highest sensitivity for individual annotations was 97%, and the highest area under the receiver operating characteristic curve was 0.98, but the quality of detection varied depending on the specific annotation.

CONCLUSIONS

Object detection AI model in small bowel CE using YOLO v5 may provide effective and easy-to-understand reading assistance. In this SEE-AI project, we open our dataset, the weights of the AI model, and a demonstration to experience our AI. We look forward to further improving the AI model in the future.

COVID-19 lateral flow test image classification using deep CNN and StyleGAN2

Introduction

Artificial intelligence (AI) in healthcare can enhance clinical workflows and diagnoses, particularly in large-scale operations like COVID-19 mass testing. This study presents a deep Convolutional Neural Network (CNN) model for automated COVID-19 RATD image classification.

Methods

To address the absence of a RATD image dataset, we crowdsourced 900 real-world images focusing on positive and negative cases. Rigorous data augmentation and StyleGAN2-ADA generated simulated images to overcome dataset limitations and class imbalances.

Results

The best CNN model achieved a 93% validation accuracy. Test accuracies were 88% for simulated datasets and 82% for real datasets. Augmenting simulated images during training did not significantly improve real-world test image performance but enhanced simulated test image performance.

Discussion

The findings of this study highlight the potential of the developed model in expediting COVID-19 testing processes and facilitating large-scale testing and tracking systems. The study also underscores the challenges in designing and developing such models, emphasizing the importance of addressing dataset limitations and class imbalances.

Conclusion

This research contributes to the deployment of large-scale testing and tracking systems, offering insights into the potential applications of AI in mitigating outbreaks similar to COVID-19. Future work could focus on refining the model and exploring its adaptability to other healthcare scenarios.

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.

Milani A, Madani Tonekaboni SA, Rabbani H, Hekmatnia A, Kafieh R. Biased Deep Learning Methods in Detection of COVID-19 Using CT Images: A Challenge Mounted by Subject-Wise-Split ISFCT Dataset

Accurate detection of respiratory system damage including COVID-19 is considered one of the crucial applications of deep learning (DL) models using CT images. However, the main shortcoming of the published works has been unreliable reported accuracy and the lack of repeatability with new datasets, mainly due to slice-wise splits of the data, creating dependency between training and test sets due to shared data across the sets. We introduce a new dataset of CT images (ISFCT Dataset) with labels indicating the subject-wise split to train and test our DL algorithms in an unbiased manner. We also use this dataset to validate the real performance of the published works in a subject-wise data split. Another key feature provides more specific labels (eight characteristic lung features) rather than being limited to COVID-19 and healthy labels. We show that the reported high accuracy of the existing models on current slice-wise splits is not repeatable for subject-wise splits, and distribution differences between data splits are demonstrated using t-distribution stochastic neighbor embedding. We indicate that, by examining subject-wise data splitting, less complicated models show competitive results compared to the exiting complicated models, demonstrating that complex models do not necessarily generate accurate and repeatable results.

Diagnostic Test Accuracy of Deep Learning Prediction Models on COVID-19 Severity: Systematic Review and Meta-Analysis

BACKGROUND

Deep learning (DL) prediction models hold great promise in the triage of COVID-19.

OBJECTIVE

We aimed to evaluate the diagnostic test accuracy of DL prediction models for assessing and predicting the severity of COVID-19.

METHODS

We searched PubMed, Scopus, LitCovid, Embase, Ovid, and the Cochrane Library for studies published from December 1, 2019, to April 30, 2022. Studies that used DL prediction models to assess or predict COVID-19 severity were included, while those without diagnostic test accuracy analysis or severity dichotomies were excluded. QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2), PROBAST (Prediction Model Risk of Bias Assessment Tool), and funnel plots were used to estimate the bias and applicability.

RESULTS

A total of 12 retrospective studies involving 2006 patients reported the cross-sectionally assessed value of DL on COVID-19 severity. The pooled sensitivity and area under the curve were 0.92 (95% CI 0.89-0.94; I²=0.00%) and 0.95 (95% CI 0.92-0.96), respectively. A total of 13 retrospective studies involving 3951 patients reported the longitudinal predictive value of DL for disease severity. The pooled sensitivity and area under the curve were 0.76 (95% CI 0.74-0.79; I²=0.00%) and 0.80 (95% CI 0.76-0.83), respectively.

CONCLUSIONS

DL prediction models can help clinicians identify potentially severe cases for early triage. However, high-quality research is lacking.

TRIAL REGISTRATION

PROSPERO CRD42022329252; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD 42022329252.

COVID-ConvNet: A Convolutional Neural Network Classifier for Diagnosing COVID-19 Infection

The novel coronavirus (COVID-19) pandemic still has a significant impact on the worldwide population's health and well-being. Effective patient screening, including radiological examination employing chest radiography as one of the main screening modalities, is an important step in the battle against the disease. Indeed, the earliest studies on COVID-19 found that patients infected with COVID-19 present with characteristic anomalies in chest radiography. In this paper, we introduce COVID-ConvNet, a deep convolutional neural network (DCNN) design suitable for detecting COVID-19 symptoms from chest X-ray (CXR) scans. The proposed deep learning (DL) model was trained and evaluated using 21,165 CXR images from the COVID-19 Database, a publicly available dataset. The experimental results demonstrate that our COVID-ConvNet model has a high prediction accuracy at 97.43% and outperforms recent related works by up to 5.9% in terms of prediction accuracy.

Chest X-Ray Images to Differentiate COVID-19 from Pneumonia with Artificial Intelligence Techniques

This paper presents an automated and noninvasive technique to discriminate COVID-19 patients from pneumonia patients using chest X-ray images and artificial intelligence. The reverse transcription-polymerase chain reaction (RT-PCR) test is commonly administered to detect COVID-19. However, the RT-PCR test necessitates person-to-person contact to administer, requires variable time to produce results, and is expensive. Moreover, this test is still unreachable to the significant global population. The chest X-ray images can play an important role here as the X-ray machines are commonly available at any healthcare facility. However, the chest X-ray images of COVID-19 and viral pneumonia patients are very similar and often lead to misdiagnosis subjectively. This investigation has employed two algorithms to solve this problem objectively. One algorithm uses lower-dimension encoded features extracted from the X-ray images and applies them to the machine learning algorithms for final classification. The other algorithm relies on the inbuilt feature extractor network to extract features from the X-ray images and classifies them with a pretrained deep neural network VGG16. The simulation results show that the proposed two algorithms can extricate COVID-19 patients from pneumonia with the best accuracy of 100% and 98.1%, employing VGG16 and the machine learning algorithm, respectively. The performances of these two algorithms have also been collated with those of other existing state-of-the-art methods.

An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

Timely and rapid diagnoses are core to informing on optimum interventions that curb the spread of COVID-19. The use of medical images such as chest X-rays and CTs has been advocated to supplement the Reverse-Transcription Polymerase Chain Reaction (RT-PCR) test, which in turn has stimulated the application of deep learning techniques in the development of automated systems for the detection of infections. Decision support systems relax the challenges inherent to the physical examination of images, which is both time consuming and requires interpretation by highly trained clinicians. A review of relevant reported studies to date shows that most deep learning algorithms utilised approaches are not amenable to implementation on resource-constrained devices. Given the rate of infections is increasing, rapid, trusted diagnoses are a central tool in the management of the spread, mandating a need for a low-cost and mobile point-of-care detection systems, especially for middle- and low-income nations. The paper presents the development and evaluation of the performance of lightweight deep learning technique for the detection of COVID-19 using the MobileNetV2 model. Results demonstrate that the performance of the lightweight deep learning model is competitive with respect to heavyweight models but delivers a significant increase in the efficiency of deployment, notably in the lowering of the cost and memory requirements of computing resources.

COVID-AleXception: A Deep Learning Model Based on a Deep Feature Concatenation Approach for the Detection of COVID-19 from Chest X-ray Images

The novel coronavirus 2019 (COVID-19) spread rapidly around the world and its outbreak has become a pandemic. Due to an increase in afflicted cases, the quantity of COVID-19 tests kits available in hospitals has decreased. Therefore, an autonomous detection system is an essential tool for reducing infection risks and spreading of the virus. In the literature, various models based on machine learning (ML) and deep learning (DL) are introduced to detect many pneumonias using chest X-ray images. The cornerstone in this paper is the use of pretrained deep learning CNN architectures to construct an automated system for COVID-19 detection and diagnosis. In this work, we used the deep feature concatenation (DFC) mechanism to combine features extracted from input images using the two modern pre-trained CNN models, AlexNet and Xception. Hence, we propose COVID-AleXception: a neural network that is a concatenation of the AlexNet and Xception models for the overall improvement of the prediction capability of this pandemic. To evaluate the proposed model and build a dataset of large-scale X-ray images, there was a careful selection of multiple X-ray images from several sources. The COVID-AleXception model can achieve a classification accuracy of 98.68%, which shows the superiority of the proposed model over AlexNet and Xception that achieved a classification accuracy of 94.86% and 95.63%, respectively. The performance results of this proposed model demonstrate its pertinence to help radiologists diagnose COVID-19 more quickly.

Prediction Model of Residual Neural Network for Pathological Confirmed Lymph Node Metastasis of Ovarian Cancer

Purpose. We want to develop a model for predicting lymph node status based on positron emission computed tomography (PET) images of untreated ovarian cancer patients. We use the feature map formed by wavelet transform and the parameters obtained by image segmentation to build the model. The model is expected to help clinicians and provide additional information about what to do with first-visit patients. Materials and Methods. Our study included 224 patients with ovarian cancer. We have chosen two main methods to extract information from images. On the one hand, we segmented the image to extract the parameters to evaluate the clustering effect. On the other hand, we used wavelet transform to extract the image’s texture information to form the image’s feature map. Based on the above two kinds of information, we used residual neural network and support vector machine for modeling. Results. We established a model to predict lymph node metastasis in patients with primary ovarian cancer using PET images. On the training set, our accuracy was 0.8854, AUC: 0.9472, CI: 0.9098-0.9752, sensitivity was 0.9865, and specificity was 0.7952. On the test set, our accuracy was 0.9104, AUC: 0.9259, CI: 0.8417-0.9889, sensitivity was 0.8125, and specificity was 1.0000. Conclusions. We used wavelet transform to process the preoperative medical images of ovarian cancer patients, and the residual neural network can effectively predict the lymph node metastasis of ovarian cancer patients, which is undoubted of great significance for patients’ staging and treatment options.